# Gemini 3.8 Flash Benchmark Scores & Performance

> Gemini 3.8 Flash by Google scores 78.41/100 overall, ranking #6 out of 411 AI models.

Canonical page: https://benchlm.ai/models/gemini-3-8-flash

Last updated: September 4, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Google |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 1M |
| Official model card | [Google DeepMind Gemini 3.8 Flash model card](https://deepmind.google/models/model-cards/gemini-3-8-flash/) |
| Overall Score | 78.41/100 |
| Overall Rank | #6 of 411 |

## Family & Coverage

- Family: Gemini 3.8 Flash
- Variant: base
- Benchmarks covered: 36 of 422
- Sibling models: [Gemini 3.8 Flash Cyber](/models/gemini-3-8-flash-cyber)
- Related earlier model: [Gemini 3.7 Flash](/models/gemini-3-7-flash)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score |
|-----------|-------|
| [Finance Agent v2](/benchmarks/financeagentv2) | 61.4% |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 89.4% |
| [Terminal-Bench 4.0](/benchmarks/terminal-bench-4) | 19.10% |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1545 |
| [OSWorld 2.0](/benchmarks/osworld2) | 59.0% |
| [AA Agentic Index](/benchmarks/aaagenticindex) | 50.0% |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 52.3% |
| [AA AutomationBench](/benchmarks/aaautomationbench) | 50.7% |
| [AA Tau3 Banking](/benchmarks/aatau3banking) | 44.9% |
| [aaTerminalBench21](/benchmarks/aaterminalbench21) | 87.6% |
| [Terminal-Bench 2.1 (Vals)](/benchmarks/valsterminalbench21) | 81.3% |

## Coding Benchmarks

| Benchmark | Score |
|-----------|-------|
| [deepSwe](/benchmarks/deepswe) | 73.8% |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 89.4% |
| [AA Coding Index](/benchmarks/aacodingindex) | 76.3% |
| [AA-SciCode](/benchmarks/aascicode) | 53.6% |
| [cursorBench32](/benchmarks/cursorbench32) | 69.2% |
| [LiveCodeBench (Vals)](/benchmarks/valslivecodebench) | 89.5% |
| [SWE-bench (Vals)](/benchmarks/valsswebench) | 80.0% |

## Multimodal & Grounded Benchmarks

| Benchmark | Score |
|-----------|-------|
| [CharXiv w/o tools](/benchmarks/charxivnotools) | 86.2% |
| [LVBench](/benchmarks/lvbench) | 87.1% |
| [AA-MMMU-Pro](/benchmarks/aammmupro) | 85.6% |
| [Design Arena Website](/benchmarks/designarenawebsite) | 1301 |

## Reasoning Benchmarks

| Benchmark | Score |
|-----------|-------|
| [AA-LCR](/benchmarks/lcr) | 81.0% |
| [CritPt](/benchmarks/critpt) | 18.3% |

## Knowledge Benchmarks

| Benchmark | Score |
|-----------|-------|
| [HLE-Verified](/benchmarks/hleverified) | 54.9% |
| [LABBench2](/benchmarks/labbench2) | 86.2% |
| [BioMysteryBench (human-solvable)](/benchmarks/biomysterybenchhumansolvable) | 88.8% |
| [BioMysteryBench (human-difficult)](/benchmarks/biomysterybenchhumandifficult) | 56.5% |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 58.7% |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 95.3% |
| [AA-HLE](/benchmarks/aahle) | 47.8% |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | 29.6% |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 54.6% |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 55.2% |
| [GPQA Diamond (Vals)](/benchmarks/valsgpqadiamond) | 94.4% |
| [MMLU-Pro (Vals)](/benchmarks/valsmmlupro) | 90.2% |

## Other Google Models

- [Gemini 3.7 Flash](/models/gemini-3-7-flash) - Score: 70.2
- [Gemini 3.6 Flash](/models/gemini-3-6-flash) - Score: 70.1
- [Gemini 3.5 Flash](/models/gemini-3-5-flash) - Score: 70
- [Gemini 3.1 Pro](/models/gemini-3-1-pro) - Score: 69.82
- [Gemini 3 Pro](/models/gemini-3-pro) - Score: 67.23
- [Gemini 3 Flash](/models/gemini-3-flash) - Score: 62.96
- [Gemini 3 Pro Deep Think](/models/gemini-3-pro-deep-think) - Score: 60.67
- [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) - Score: 60.5
- [Gemma 4 31B](/models/gemma-4-31b) - Score: 58.69
- [Gemini 2.5 Pro](/models/gemini-2-5-pro) - Score: 57.98
- [Gemma 4 26B A4B](/models/gemma-4-26b-a4b) - Score: 56.66
- [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite) - Score: 56.13
- [Gemini 2.5 Flash](/models/gemini-2-5-flash) - Score: 51.68
- [Gemma 4 12B](/models/gemma-4-12b) - Score: 46.64
- [Gemma 4 E4B](/models/gemma-4-e4b) - Score: 42.92
- [Gemma 4 E2B](/models/gemma-4-e2b) - Score: 41.94
- [Gemma 3 27B](/models/gemma-3-27b) - Score: 38.2
- [Gemini 1.5 Pro](/models/gemini-1-5-pro) - Score: 34.88
- [Gemini 1.0 Pro](/models/gemini-1-0-pro) - Score: 15.31
- [Gemini 3.8 Flash Cyber](/models/gemini-3-8-flash-cyber) - Score: not computed
- [Gemini 3.5 Flash Cyber](/models/gemini-3-5-flash-cyber) - Score: not computed
- [Gemini 3.1 Flash TTS Preview](/models/gemini-3-1-flash-tts-preview) - Score: not computed
- [Gemini 2.5 Flash Native Audio Preview (12-2025)](/models/gemini-2-5-flash-native-audio-preview-12-2025) - Score: not computed
- [Gemini 2.5 Flash TTS Preview](/models/gemini-2-5-flash-tts-preview) - Score: not computed
- [Gemini 2.5 Pro TTS Preview](/models/gemini-2-5-pro-tts-preview) - Score: not computed
- [Gemini 3.1 Flash Live Preview](/models/gemini-3-1-flash-live-preview) - Score: not computed